Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    special characters followed by code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     team
    0.90
     팀
    0.80
     टीम
    0.80
    team
    0.80
     Team
    0.78
    チーム
    0.77
     تیم
    0.77
    팀
    0.77
    团队
    0.71
     TEAM
    0.71
    POSITIVE LOGITS
    тов
    0.39
    ジャー
    0.36
    Browser
    0.36
    ov
    0.35
    veget
    0.35
    Digest
    0.35
    Props
    0.35
    toy
    0.34
    Heath
    0.33
     veteran
    0.33
    Act Density 0.008%

    No Known Activations